# !pip install git+https://github.com/alberanid/imdbpy
# !pip install pandas
# !pip install numpy
# !pip install matplotlib
# !pip install seaborn
# !pip install pandas_profiling --upgrade
# !pip install plotly
# !pip install wordcloud
# !pip install Flask
# Import Dataset
# Import File from Loacal Drive
# from google.colab import files
# data_to_load = files.upload()
# from google.colab import drive
# drive.mount('/content/drive')
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
import collections
import plotly.express as px
import plotly.graph_objects as go
import nltk
import re
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk.probability import FreqDist
from nltk.util import ngrams
from plotly.subplots import make_subplots
from plotly.offline import iplot, init_notebook_mode
from wordcloud import WordCloud, STOPWORDS
from pandas_profiling import ProfileReport
%matplotlib inline
warnings.filterwarnings("ignore")
nltk.download('all')
[nltk_data] Downloading collection 'all' [nltk_data] | [nltk_data] | Downloading package abc to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package abc is already up-to-date! [nltk_data] | Downloading package alpino to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package alpino is already up-to-date! [nltk_data] | Downloading package biocreative_ppi to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package biocreative_ppi is already up-to-date! [nltk_data] | Downloading package brown to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package brown is already up-to-date! [nltk_data] | Downloading package brown_tei to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package brown_tei is already up-to-date! [nltk_data] | Downloading package cess_cat to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package cess_cat is already up-to-date! [nltk_data] | Downloading package cess_esp to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package cess_esp is already up-to-date! [nltk_data] | Downloading package chat80 to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package chat80 is already up-to-date! [nltk_data] | Downloading package city_database to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package city_database is already up-to-date! [nltk_data] | Downloading package cmudict to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package cmudict is already up-to-date! [nltk_data] | Downloading package comparative_sentences to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package comparative_sentences is already up-to- [nltk_data] | date! [nltk_data] | Downloading package comtrans to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package comtrans is already up-to-date! [nltk_data] | Downloading package conll2000 to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package conll2000 is already up-to-date! [nltk_data] | Downloading package conll2002 to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package conll2002 is already up-to-date! [nltk_data] | Downloading package conll2007 to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package conll2007 is already up-to-date! [nltk_data] | Downloading package crubadan to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package crubadan is already up-to-date! [nltk_data] | Downloading package dependency_treebank to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package dependency_treebank is already up-to-date! [nltk_data] | Downloading package dolch to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package dolch is already up-to-date! [nltk_data] | Downloading package europarl_raw to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package europarl_raw is already up-to-date! [nltk_data] | Downloading package floresta to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package floresta is already up-to-date! [nltk_data] | Downloading package framenet_v15 to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package framenet_v15 is already up-to-date! [nltk_data] | Downloading package framenet_v17 to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package framenet_v17 is already up-to-date! [nltk_data] | Downloading package gazetteers to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package gazetteers is already up-to-date! [nltk_data] | Downloading package genesis to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package genesis is already up-to-date! [nltk_data] | Downloading package gutenberg to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package gutenberg is already up-to-date! [nltk_data] | Downloading package ieer to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package ieer is already up-to-date! [nltk_data] | Downloading package inaugural to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package inaugural is already up-to-date! [nltk_data] | Downloading package indian to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package indian is already up-to-date! [nltk_data] | Downloading package jeita to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package jeita is already up-to-date! [nltk_data] | Downloading package kimmo to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package kimmo is already up-to-date! [nltk_data] | Downloading package knbc to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package knbc is already up-to-date! [nltk_data] | Downloading package lin_thesaurus to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package lin_thesaurus is already up-to-date! [nltk_data] | Downloading package mac_morpho to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package mac_morpho is already up-to-date! [nltk_data] | Downloading package machado to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package machado is already up-to-date! [nltk_data] | Downloading package masc_tagged to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package masc_tagged is already up-to-date! [nltk_data] | Downloading package moses_sample to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package moses_sample is already up-to-date! [nltk_data] | Downloading package movie_reviews to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package movie_reviews is already up-to-date! [nltk_data] | Downloading package names to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package names is already up-to-date! [nltk_data] | Downloading package nombank.1.0 to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package nombank.1.0 is already up-to-date! [nltk_data] | Downloading package nps_chat to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package nps_chat is already up-to-date! [nltk_data] | Downloading package omw to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package omw is already up-to-date! [nltk_data] | Downloading package opinion_lexicon to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package opinion_lexicon is already up-to-date! [nltk_data] | Downloading package paradigms to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package paradigms is already up-to-date! [nltk_data] | Downloading package pil to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package pil is already up-to-date! [nltk_data] | Downloading package pl196x to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package pl196x is already up-to-date! [nltk_data] | Downloading package ppattach to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package ppattach is already up-to-date! [nltk_data] | Downloading package problem_reports to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package problem_reports is already up-to-date! [nltk_data] | Downloading package propbank to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package propbank is already up-to-date! [nltk_data] | Downloading package ptb to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package ptb is already up-to-date! [nltk_data] | Downloading package product_reviews_1 to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package product_reviews_1 is already up-to-date! [nltk_data] | Downloading package product_reviews_2 to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package product_reviews_2 is already up-to-date! [nltk_data] | Downloading package pros_cons to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package pros_cons is already up-to-date! [nltk_data] | Downloading package qc to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package qc is already up-to-date! [nltk_data] | Downloading package reuters to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package reuters is already up-to-date! [nltk_data] | Downloading package rte to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package rte is already up-to-date! [nltk_data] | Downloading package semcor to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package semcor is already up-to-date! [nltk_data] | Downloading package senseval to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package senseval is already up-to-date! [nltk_data] | Downloading package sentiwordnet to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package sentiwordnet is already up-to-date! [nltk_data] | Downloading package sentence_polarity to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package sentence_polarity is already up-to-date! [nltk_data] | Downloading package shakespeare to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package shakespeare is already up-to-date! [nltk_data] | Downloading package sinica_treebank to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package sinica_treebank is already up-to-date! [nltk_data] | Downloading package smultron to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package smultron is already up-to-date! [nltk_data] | Downloading package state_union to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package state_union is already up-to-date! [nltk_data] | Downloading package stopwords to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package stopwords is already up-to-date! [nltk_data] | Downloading package subjectivity to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package subjectivity is already up-to-date! [nltk_data] | Downloading package swadesh to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package swadesh is already up-to-date! [nltk_data] | Downloading package switchboard to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package switchboard is already up-to-date! [nltk_data] | Downloading package timit to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package timit is already up-to-date! [nltk_data] | Downloading package toolbox to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package toolbox is already up-to-date! [nltk_data] | Downloading package treebank to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package treebank is already up-to-date! [nltk_data] | Downloading package twitter_samples to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package twitter_samples is already up-to-date! [nltk_data] | Downloading package udhr to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package udhr is already up-to-date! [nltk_data] | Downloading package udhr2 to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package udhr2 is already up-to-date! [nltk_data] | Downloading package unicode_samples to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package unicode_samples is already up-to-date! [nltk_data] | Downloading package universal_treebanks_v20 to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package universal_treebanks_v20 is already up-to- [nltk_data] | date! [nltk_data] | Downloading package verbnet to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package verbnet is already up-to-date! [nltk_data] | Downloading package verbnet3 to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package verbnet3 is already up-to-date! [nltk_data] | Downloading package webtext to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package webtext is already up-to-date! [nltk_data] | Downloading package wordnet to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package wordnet is already up-to-date! [nltk_data] | Downloading package wordnet_ic to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package wordnet_ic is already up-to-date! [nltk_data] | Downloading package words to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package words is already up-to-date! [nltk_data] | Downloading package ycoe to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package ycoe is already up-to-date! [nltk_data] | Downloading package rslp to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package rslp is already up-to-date! [nltk_data] | Downloading package maxent_treebank_pos_tagger to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package maxent_treebank_pos_tagger is already up- [nltk_data] | to-date! [nltk_data] | Downloading package universal_tagset to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package universal_tagset is already up-to-date! [nltk_data] | Downloading package maxent_ne_chunker to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package maxent_ne_chunker is already up-to-date! [nltk_data] | Downloading package punkt to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package punkt is already up-to-date! [nltk_data] | Downloading package book_grammars to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package book_grammars is already up-to-date! [nltk_data] | Downloading package sample_grammars to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package sample_grammars is already up-to-date! [nltk_data] | Downloading package spanish_grammars to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package spanish_grammars is already up-to-date! [nltk_data] | Downloading package basque_grammars to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package basque_grammars is already up-to-date! [nltk_data] | Downloading package large_grammars to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package large_grammars is already up-to-date! [nltk_data] | Downloading package tagsets to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package tagsets is already up-to-date! [nltk_data] | Downloading package snowball_data to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package snowball_data is already up-to-date! [nltk_data] | Downloading package bllip_wsj_no_aux to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package bllip_wsj_no_aux is already up-to-date! [nltk_data] | Downloading package word2vec_sample to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package word2vec_sample is already up-to-date! [nltk_data] | Downloading package panlex_swadesh to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package panlex_swadesh is already up-to-date! [nltk_data] | Downloading package mte_teip5 to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package mte_teip5 is already up-to-date! [nltk_data] | Downloading package averaged_perceptron_tagger to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package averaged_perceptron_tagger is already up- [nltk_data] | to-date! [nltk_data] | Downloading package averaged_perceptron_tagger_ru to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package averaged_perceptron_tagger_ru is already [nltk_data] | up-to-date! [nltk_data] | Downloading package perluniprops to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package perluniprops is already up-to-date! [nltk_data] | Downloading package nonbreaking_prefixes to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package nonbreaking_prefixes is already up-to-date! [nltk_data] | Downloading package vader_lexicon to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package vader_lexicon is already up-to-date! [nltk_data] | Downloading package porter_test to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package porter_test is already up-to-date! [nltk_data] | Downloading package wmt15_eval to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package wmt15_eval is already up-to-date! [nltk_data] | Downloading package mwa_ppdb to [nltk_data] | C:\Users\pawan\AppData\Roaming\nltk_data... [nltk_data] | Package mwa_ppdb is already up-to-date! [nltk_data] | [nltk_data] Done downloading collection all
True
# path = '/content/drive/MyDrive/Files/'
path = 'C:\\Users\\pawan\\OneDrive\\Desktop\\ott\\Data\\'
df_tvshows = pd.read_csv(path + 'otttvshows.csv')
df_tvshows.head()
| ID | Title | Year | Age | IMDb | Rotten Tomatoes | Directors | Cast | Genres | Country | Language | Plotline | Runtime | Kind | Seasons | Netflix | Hulu | Prime Video | Disney+ | Type | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 1 | Snowpiercer | 2013 | 18+ | 6.9 | 94% | NaN | Daveed Diggs,Iddo Goldberg,Mickey Sumner,Aliso... | Action,Drama,Sci-Fi,Thriller | United States | English | Set seven years after the world has become a f... | 60.0 | tv series | 3.0 | 1 | 0 | 0 | 0 | 1 |
| 1 | 2 | Philadelphia | 1993 | 13+ | 8.8 | 80% | NaN | Charlie Day,Glenn Howerton,Rob McElhenney,Kait... | Comedy | United States | English | The gang, 5 raging alcoholic, narcissists run ... | 22.0 | tv series | 18.0 | 1 | 0 | 0 | 0 | 1 |
| 2 | 3 | Roma | 2018 | 18+ | 8.7 | 93% | NaN | Kevin McKidd,Ray Stevenson,Polly Walker,Kerry ... | Action,Drama,History,Romance,War | United Kingdom,United States | English | In this British historical drama, the turbulen... | 52.0 | tv series | 2.0 | 1 | 0 | 0 | 0 | 1 |
| 3 | 4 | Amy | 2015 | 18+ | 7.0 | 87% | NaN | Amy Brenneman,Richard T. Jones,Jessica Tuck,Ma... | Drama | United States | English | A family drama focused on three generations of... | 60.0 | tv series | 6.0 | 1 | 0 | 1 | 1 | 1 |
| 4 | 5 | The Young Offenders | 2016 | NaN | 8.0 | 100% | NaN | Alex Murphy,Chris Walley,Hilary Rose,Dominic M... | Comedy | United Kingdom,Ireland | English | NaN | 30.0 | tv series | 3.0 | 1 | 0 | 0 | 0 | 1 |
# profile = ProfileReport(df_tvshows)
# profile
def data_investigate(df):
print('No of Rows : ', df.shape[0])
print('No of Coloums : ', df.shape[1])
print('**'*25)
print('Colums Names : \n', df.columns)
print('**'*25)
print('Datatype of Columns : \n', df.dtypes)
print('**'*25)
print('Missing Values : ')
c = df.isnull().sum()
c = c[c > 0]
print(c)
print('**'*25)
print('Missing vaules %age wise :\n')
print((100*(df.isnull().sum()/len(df.index))))
print('**'*25)
print('Pictorial Representation : ')
plt.figure(figsize = (10, 10))
sns.heatmap(df.isnull(), yticklabels = False, cbar = False)
plt.show()
data_investigate(df_tvshows)
No of Rows : 5432
No of Coloums : 20
**************************************************
Colums Names :
Index(['ID', 'Title', 'Year', 'Age', 'IMDb', 'Rotten Tomatoes', 'Directors',
'Cast', 'Genres', 'Country', 'Language', 'Plotline', 'Runtime', 'Kind',
'Seasons', 'Netflix', 'Hulu', 'Prime Video', 'Disney+', 'Type'],
dtype='object')
**************************************************
Datatype of Columns :
ID int64
Title object
Year int64
Age object
IMDb float64
Rotten Tomatoes object
Directors object
Cast object
Genres object
Country object
Language object
Plotline object
Runtime float64
Kind object
Seasons float64
Netflix int64
Hulu int64
Prime Video int64
Disney+ int64
Type int64
dtype: object
**************************************************
Missing Values :
Age 1954
IMDb 556
Rotten Tomatoes 4194
Directors 5158
Cast 486
Genres 323
Country 549
Language 638
Plotline 2493
Runtime 1410
Seasons 679
dtype: int64
**************************************************
Missing vaules %age wise :
ID 0.000000
Title 0.000000
Year 0.000000
Age 35.972018
IMDb 10.235641
Rotten Tomatoes 77.209131
Directors 94.955817
Cast 8.946981
Genres 5.946244
Country 10.106775
Language 11.745214
Plotline 45.894698
Runtime 25.957290
Kind 0.000000
Seasons 12.500000
Netflix 0.000000
Hulu 0.000000
Prime Video 0.000000
Disney+ 0.000000
Type 0.000000
dtype: float64
**************************************************
Pictorial Representation :
# ID
# df_tvshows = df_tvshows.drop(['ID'], axis = 1)
# Age
df_tvshows.loc[df_tvshows['Age'].isnull() & df_tvshows['Disney+'] == 1, "Age"] = '13'
# df_tvshows.fillna({'Age' : 18}, inplace = True)
df_tvshows.fillna({'Age' : 'NR'}, inplace = True)
df_tvshows['Age'].replace({'all': '0'}, inplace = True)
df_tvshows['Age'].replace({'7+': '7'}, inplace = True)
df_tvshows['Age'].replace({'13+': '13'}, inplace = True)
df_tvshows['Age'].replace({'16+': '16'}, inplace = True)
df_tvshows['Age'].replace({'18+': '18'}, inplace = True)
# df_tvshows['Age'] = df_tvshows['Age'].astype(int)
# IMDb
# df_tvshows.fillna({'IMDb' : df_tvshows['IMDb'].mean()}, inplace = True)
# df_tvshows.fillna({'IMDb' : df_tvshows['IMDb'].median()}, inplace = True)
df_tvshows.fillna({'IMDb' : "NA"}, inplace = True)
# Rotten Tomatoes
df_tvshows['Rotten Tomatoes'] = df_tvshows['Rotten Tomatoes'][df_tvshows['Rotten Tomatoes'].notnull()].str.replace('%', '').astype(int)
# df_tvshows['Rotten Tomatoes'] = df_tvshows['Rotten Tomatoes'][df_tvshows['Rotten Tomatoes'].notnull()].astype(int)
# df_tvshows.fillna({'Rotten Tomatoes' : df_tvshows['Rotten Tomatoes'].mean()}, inplace = True)
# df_tvshows.fillna({'Rotten Tomatoes' : df_tvshows['Rotten Tomatoes'].median()}, inplace = True)
# df_tvshows['Rotten Tomatoes'] = df_tvshows['Rotten Tomatoes'].astype(int)
df_tvshows.fillna({'Rotten Tomatoes' : "NA"}, inplace = True)
# Directors
# df_tvshows = df_tvshows.drop(['Directors'], axis = 1)
df_tvshows.fillna({'Directors' : "NA"}, inplace = True)
# Cast
df_tvshows.fillna({'Cast' : "NA"}, inplace = True)
# Genres
df_tvshows.fillna({'Genres': "NA"}, inplace = True)
# Country
df_tvshows.fillna({'Country': "NA"}, inplace = True)
# Language
df_tvshows.fillna({'Language': "NA"}, inplace = True)
# Plotline
df_tvshows.fillna({'Plotline': "NA"}, inplace = True)
# Runtime
# df_tvshows.fillna({'Runtime' : df_tvshows['Runtime'].mean()}, inplace = True)
# df_tvshows['Runtime'] = df_tvshows['Runtime'].astype(int)
df_tvshows.fillna({'Runtime' : "NA"}, inplace = True)
# Kind
# df_tvshows.fillna({'Kind': "NA"}, inplace = True)
# Type
# df_tvshows.fillna({'Type': "NA"}, inplace = True)
# df_tvshows = df_tvshows.drop(['Type'], axis = 1)
# Seasons
# df_tvshows.fillna({'Seasons': 1}, inplace = True)
df_tvshows.fillna({'Seasons': "NA"}, inplace = True)
# df_tvshows = df_tvshows.drop(['Seasons'], axis = 1)
# df_tvshows['Seasons'] = df_tvshows['Seasons'].astype(int)
# df_tvshows.fillna({'Seasons' : df_tvshows['Seasons'].mean()}, inplace = True)
# df_tvshows['Seasons'] = df_tvshows['Seasons'].astype(int)
# Service Provider
df_tvshows['Service Provider'] = df_tvshows.loc[:, ['Netflix', 'Prime Video', 'Disney+', 'Hulu']].idxmax(axis = 1)
# df_tvshows.drop(['Netflix','Prime Video','Disney+','Hulu'], axis = 1)
# Removing Duplicate and Missing Entries
df_tvshows.dropna(how = 'any', inplace = True)
df_tvshows.drop_duplicates(inplace = True)
data_investigate(df_tvshows)
No of Rows : 5432
No of Coloums : 21
**************************************************
Colums Names :
Index(['ID', 'Title', 'Year', 'Age', 'IMDb', 'Rotten Tomatoes', 'Directors',
'Cast', 'Genres', 'Country', 'Language', 'Plotline', 'Runtime', 'Kind',
'Seasons', 'Netflix', 'Hulu', 'Prime Video', 'Disney+', 'Type',
'Service Provider'],
dtype='object')
**************************************************
Datatype of Columns :
ID int64
Title object
Year int64
Age object
IMDb object
Rotten Tomatoes object
Directors object
Cast object
Genres object
Country object
Language object
Plotline object
Runtime object
Kind object
Seasons object
Netflix int64
Hulu int64
Prime Video int64
Disney+ int64
Type int64
Service Provider object
dtype: object
**************************************************
Missing Values :
Series([], dtype: int64)
**************************************************
Missing vaules %age wise :
ID 0.0
Title 0.0
Year 0.0
Age 0.0
IMDb 0.0
Rotten Tomatoes 0.0
Directors 0.0
Cast 0.0
Genres 0.0
Country 0.0
Language 0.0
Plotline 0.0
Runtime 0.0
Kind 0.0
Seasons 0.0
Netflix 0.0
Hulu 0.0
Prime Video 0.0
Disney+ 0.0
Type 0.0
Service Provider 0.0
dtype: float64
**************************************************
Pictorial Representation :
df_tvshows.head()
| ID | Title | Year | Age | IMDb | Rotten Tomatoes | Directors | Cast | Genres | Country | ... | Plotline | Runtime | Kind | Seasons | Netflix | Hulu | Prime Video | Disney+ | Type | Service Provider | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 1 | Snowpiercer | 2013 | 18 | 6.9 | 94 | NA | Daveed Diggs,Iddo Goldberg,Mickey Sumner,Aliso... | Action,Drama,Sci-Fi,Thriller | United States | ... | Set seven years after the world has become a f... | 60 | tv series | 3 | 1 | 0 | 0 | 0 | 1 | Netflix |
| 1 | 2 | Philadelphia | 1993 | 13 | 8.8 | 80 | NA | Charlie Day,Glenn Howerton,Rob McElhenney,Kait... | Comedy | United States | ... | The gang, 5 raging alcoholic, narcissists run ... | 22 | tv series | 18 | 1 | 0 | 0 | 0 | 1 | Netflix |
| 2 | 3 | Roma | 2018 | 18 | 8.7 | 93 | NA | Kevin McKidd,Ray Stevenson,Polly Walker,Kerry ... | Action,Drama,History,Romance,War | United Kingdom,United States | ... | In this British historical drama, the turbulen... | 52 | tv series | 2 | 1 | 0 | 0 | 0 | 1 | Netflix |
| 3 | 4 | Amy | 2015 | 18 | 7 | 87 | NA | Amy Brenneman,Richard T. Jones,Jessica Tuck,Ma... | Drama | United States | ... | A family drama focused on three generations of... | 60 | tv series | 6 | 1 | 0 | 1 | 1 | 1 | Netflix |
| 4 | 5 | The Young Offenders | 2016 | NR | 8 | 100 | NA | Alex Murphy,Chris Walley,Hilary Rose,Dominic M... | Comedy | United Kingdom,Ireland | ... | NA | 30 | tv series | 3 | 1 | 0 | 0 | 0 | 1 | Netflix |
5 rows × 21 columns
df_tvshows.describe()
| ID | Year | Netflix | Hulu | Prime Video | Disney+ | Type | |
|---|---|---|---|---|---|---|---|
| count | 5432.000000 | 5432.000000 | 5432.000000 | 5432.000000 | 5432.000000 | 5432.000000 | 5432.0 |
| mean | 2716.500000 | 2010.668446 | 0.341311 | 0.293999 | 0.403351 | 0.033689 | 1.0 |
| std | 1568.227662 | 11.726176 | 0.474193 | 0.455633 | 0.490615 | 0.180445 | 0.0 |
| min | 1.000000 | 1901.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 1.0 |
| 25% | 1358.750000 | 2009.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 1.0 |
| 50% | 2716.500000 | 2014.000000 | 0.000000 | 0.000000 | 0.000000 | 0.000000 | 1.0 |
| 75% | 4074.250000 | 2017.000000 | 1.000000 | 1.000000 | 1.000000 | 0.000000 | 1.0 |
| max | 5432.000000 | 2020.000000 | 1.000000 | 1.000000 | 1.000000 | 1.000000 | 1.0 |
df_tvshows.corr()
| ID | Year | Netflix | Hulu | Prime Video | Disney+ | Type | |
|---|---|---|---|---|---|---|---|
| ID | 1.000000 | -0.031346 | -0.646330 | 0.034293 | 0.441264 | 0.195409 | NaN |
| Year | -0.031346 | 1.000000 | 0.222316 | -0.065807 | -0.198675 | -0.022741 | NaN |
| Netflix | -0.646330 | 0.222316 | 1.000000 | -0.366515 | -0.515086 | -0.119344 | NaN |
| Hulu | 0.034293 | -0.065807 | -0.366515 | 1.000000 | -0.377374 | -0.075701 | NaN |
| Prime Video | 0.441264 | -0.198675 | -0.515086 | -0.377374 | 1.000000 | -0.151442 | NaN |
| Disney+ | 0.195409 | -0.022741 | -0.119344 | -0.075701 | -0.151442 | 1.000000 | NaN |
| Type | NaN | NaN | NaN | NaN | NaN | NaN | NaN |
# df_tvshows.sort_values('Year', ascending = True)
# df_tvshows.sort_values('IMDb', ascending = False)
# df_tvshows.to_csv(path_or_buf= '/content/drive/MyDrive/Files/updated_otttvshows.csv', index = False)
# path = '/content/drive/MyDrive/Files/'
# udf_tvshows = pd.read_csv(path + 'updated_otttvshows.csv')
# udf_tvshows
# df_netflix_tvshows = df_tvshows.loc[(df_tvshows['Netflix'] > 0)]
# df_hulu_tvshows = df_tvshows.loc[(df_tvshows['Hulu'] > 0)]
# df_prime_video_tvshows = df_tvshows.loc[(df_tvshows['Prime Video'] > 0)]
# df_disney_tvshows = df_tvshows.loc[(df_tvshows['Disney+'] > 0)]
df_netflix_only_tvshows = df_tvshows[(df_tvshows['Netflix'] == 1) & (df_tvshows['Hulu'] == 0) & (df_tvshows['Prime Video'] == 0 ) & (df_tvshows['Disney+'] == 0)]
df_hulu_only_tvshows = df_tvshows[(df_tvshows['Netflix'] == 0) & (df_tvshows['Hulu'] == 1) & (df_tvshows['Prime Video'] == 0 ) & (df_tvshows['Disney+'] == 0)]
df_prime_video_only_tvshows = df_tvshows[(df_tvshows['Netflix'] == 0) & (df_tvshows['Hulu'] == 0) & (df_tvshows['Prime Video'] == 1 ) & (df_tvshows['Disney+'] == 0)]
df_disney_only_tvshows = df_tvshows[(df_tvshows['Netflix'] == 0) & (df_tvshows['Hulu'] == 0) & (df_tvshows['Prime Video'] == 0 ) & (df_tvshows['Disney+'] == 1)]
df_tvshows_imdb = df_tvshows.copy()
df_tvshows_imdb.drop(df_tvshows_imdb.loc[df_tvshows_imdb['IMDb'] == "NA"].index, inplace = True)
# df_tvshows_imdb = df_tvshows_imdb[df_tvshows_imdb.IMDb != "NA"]
df_tvshows_imdb['IMDb'] = df_tvshows_imdb['IMDb'].astype(int)
# Creating distinct dataframes only with the tvshows present on individual streaming platforms
netflix_imdb_tvshows = df_tvshows_imdb.loc[df_tvshows_imdb['Netflix'] == 1]
hulu_imdb_tvshows = df_tvshows_imdb.loc[df_tvshows_imdb['Hulu'] == 1]
prime_video_imdb_tvshows = df_tvshows_imdb.loc[df_tvshows_imdb['Prime Video'] == 1]
disney_imdb_tvshows = df_tvshows_imdb.loc[df_tvshows_imdb['Disney+'] == 1]
df_tvshows_imdb_group = df_tvshows_imdb.copy()
plt.figure(figsize = (10, 10))
corr = df_tvshows_imdb.corr()
# Plot figsize
fig, ax = plt.subplots(figsize=(10, 8))
# Generate Heat Map, allow annotations and place floats in map
sns.heatmap(corr, cmap = 'magma', annot = True, fmt = ".2f")
# Apply xticks
plt.xticks(range(len(corr.columns)), corr.columns);
# Apply yticks
plt.yticks(range(len(corr.columns)), corr.columns)
# show plot
plt.show()
fig.show()
<Figure size 720x720 with 0 Axes>
df_imdb_high_tvshows = df_tvshows_imdb.sort_values(by = 'IMDb', ascending = False).reset_index()
df_imdb_high_tvshows = df_imdb_high_tvshows.drop(['index'], axis = 1)
# filter = (df_tvshows_imdb['IMDb'] == (df_tvshows_imdb['IMDb'].max()))
# df_imdb_high_tvshows = df_tvshows_imdb[filter]
# highest_rated_tvshows = df_tvshows_imdb.loc[df_tvshows_imdb['IMDb'].idxmax()]
print('\nTV Shows with Highest Ever IMDb are : \n')
df_imdb_high_tvshows.head(5)
TV Shows with Highest Ever IMDb are :
| ID | Title | Year | Age | IMDb | Rotten Tomatoes | Directors | Cast | Genres | Country | ... | Plotline | Runtime | Kind | Seasons | Netflix | Hulu | Prime Video | Disney+ | Type | Service Provider | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 5129 | Tanks! | 2005 | 7 | 10 | NA | NA | David Fletcher,Graham McTavish,John Erickson,B... | History,War | United States | ... | In this series Tom Hubbard travels throughout ... | NA | tv series | 1 | 0 | 0 | 1 | 0 | 1 | Prime Video |
| 1 | 3718 | The Sopranos | 1999 | 18 | 9 | 92 | NA | James Gandolfini,Edie Falco,Michael Imperioli,... | Crime,Drama | United States | ... | Harry Bosch is an irreverent homicide detectiv... | 55 | tv series | 6 | 0 | 0 | 1 | 0 | 1 | Prime Video |
| 2 | 144 | The Chosen | 1981 | 7 | 9 | 75 | NA | Shahar Isaac,Jonathan Roumie,Noah James,Paras ... | Drama,History | United States | ... | Depressed after the passing of his father (Dha... | 54 | tv series | 2 | 0 | 0 | 1 | 0 | 1 | Prime Video |
| 3 | 835 | Africa | 2013 | 7 | 9 | NA | NA | David Attenborough,Simon Blakeney,James Aldred... | Documentary | United Kingdom | ... | Three ordinary teenage girls discover a moon p... | 360 | tv series | 1 | 1 | 0 | 0 | 0 | 1 | Netflix |
| 4 | 5304 | The Imagineering Story | 2019 | 0 | 9 | 100 | NA | Tom Morris,Kevin Rafferty,Angela Bassett,Tom F... | Documentary | United States | ... | Raven Baxter is a teenager. She can see glimps... | 60 | tv series | 1 | 0 | 0 | 0 | 1 | 1 | Disney+ |
5 rows × 21 columns
fig = px.bar(y = df_imdb_high_tvshows['Title'][:15],
x = df_imdb_high_tvshows['IMDb'][:15],
color = df_imdb_high_tvshows['IMDb'][:15],
color_continuous_scale = 'Teal_r',
labels = { 'y' : 'TV Shows', 'x' : 'IMDb : Rating'},
title = 'TV Shows with Highest IMDb : All Platforms')
fig.update_layout(plot_bgcolor = 'white')
fig.show()
df_imdb_low_tvshows = df_tvshows_imdb.sort_values(by = 'IMDb', ascending = True).reset_index()
df_imdb_low_tvshows = df_imdb_low_tvshows.drop(['index'], axis = 1)
# filter = (df_tvshows_imdb['IMDb'] == (df_tvshows_imdb['IMDb'].min()))
# df_imdb_low_tvshows = df_tvshows_imdb[filter]
print('\nTV Shows with Lowest Ever IMDb are : \n')
df_imdb_low_tvshows.head(5)
TV Shows with Lowest Ever IMDb are :
| ID | Title | Year | Age | IMDb | Rotten Tomatoes | Directors | Cast | Genres | Country | ... | Plotline | Runtime | Kind | Seasons | Netflix | Hulu | Prime Video | Disney+ | Type | Service Provider | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 5245 | PINKFONG! | 2017 | NR | 1 | NA | NA | Marie Segoine | Family | NA | ... | NA | NA | tv series | 1 | 0 | 0 | 1 | 0 | 1 | Prime Video |
| 1 | 3368 | My Super Sweet 16 | 2005 | 7 | 1 | NA | NA | Mary Morrison,Quincy Brown,Shad Moss,Cher Hubs... | Documentary,Reality-TV | United States | ... | Geologist Martin Pepper and Biologist Liz Bonn... | 30 | tv series | 10 | 0 | 1 | 0 | 0 | 1 | Hulu |
| 2 | 3336 | Toddlers & Tiaras | 2009 | 7 | 1 | NA | NA | MaKenzie Myers,Dawn Rochelle,Wendy D. Lee,Alan... | Reality-TV | United States | ... | NA | NA | tv series | 7 | 0 | 1 | 1 | 0 | 1 | Prime Video |
| 3 | 4820 | Pinkfong! Baby Shark Special | 2017 | NR | 1 | NA | NA | Marie Segoine | Family | NA | ... | The Bumble Nums are back with all new adventur... | NA | tv series | 1 | 0 | 0 | 1 | 0 | 1 | Prime Video |
| 4 | 338 | 12-12-12 | 2012 | 18 | 1 | NA | NA | Colin Murray,John Hartson,Robbie Savage | Sport | NA | ... | Hugo (Gabriel Byrne), heir to a fortune, is ma... | NA | tv series | NA | 0 | 0 | 1 | 0 | 1 | Prime Video |
5 rows × 21 columns
fig = px.bar(y = df_imdb_low_tvshows['Title'][:15],
x = df_imdb_low_tvshows['IMDb'][:15],
color = df_imdb_low_tvshows['IMDb'][:15],
color_continuous_scale = 'Teal_r',
labels = { 'y' : 'TV Shows', 'x' : 'IMDb : Rating'},
title = 'TV Shows with Lowest IMDb : All Platforms')
fig.update_layout(plot_bgcolor = 'white')
fig.show()
print(f'''
Total '{df_tvshows_imdb['IMDb'].unique().shape[0]}' unique IMDb s were Given, They were Like this,\n
{df_tvshows_imdb.sort_values(by = 'IMDb', ascending = False)['IMDb'].unique()}\n
The Highest Ever IMDb Ever Any TV Show Got is '{df_imdb_high_tvshows['Title'][0]}' : '{df_imdb_high_tvshows['IMDb'].max()}'\n
The Lowest Ever IMDb Ever Any TV Show Got is '{df_imdb_low_tvshows['Title'][0]}' : '{df_imdb_low_tvshows['IMDb'].min()}'\n
''')
Total '10' unique IMDb s were Given, They were Like this,
[10 9 8 7 6 5 4 3 2 1]
The Highest Ever IMDb Ever Any TV Show Got is 'Tanks!' : '10'
The Lowest Ever IMDb Ever Any TV Show Got is 'PINKFONG!' : '1'
netflix_imdb_high_tvshows = df_imdb_high_tvshows.loc[df_imdb_high_tvshows['Netflix']==1].reset_index()
netflix_imdb_high_tvshows = netflix_imdb_high_tvshows.drop(['index'], axis = 1)
netflix_imdb_low_tvshows = df_imdb_low_tvshows.loc[df_imdb_low_tvshows['Netflix']==1].reset_index()
netflix_imdb_low_tvshows = netflix_imdb_low_tvshows.drop(['index'], axis = 1)
netflix_imdb_high_tvshows.head(5)
| ID | Title | Year | Age | IMDb | Rotten Tomatoes | Directors | Cast | Genres | Country | ... | Plotline | Runtime | Kind | Seasons | Netflix | Hulu | Prime Video | Disney+ | Type | Service Provider | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 835 | Africa | 2013 | 7 | 9 | NA | NA | David Attenborough,Simon Blakeney,James Aldred... | Documentary | United Kingdom | ... | Three ordinary teenage girls discover a moon p... | 360 | tv series | 1 | 1 | 0 | 0 | 0 | 1 | Netflix |
| 1 | 779 | Yeh Meri Family | 2018 | 16 | 9 | NA | NA | Vishesh Bansal,Mona Singh,Akarsh Khurana,Ahan ... | Comedy,Drama,Family,Musical,Romance | India | ... | Three teen strangers wake up in a mysterious l... | 30 | tv series | 1 | 1 | 0 | 0 | 0 | 1 | Netflix |
| 2 | 1576 | Raja Rasoi Aur Anya Kahaniyan | 2015 | NR | 9 | NA | NA | Manwendra Tripathy | History | India | ... | Amamiya Shuuhei moves from Tokyo to the countr... | 45 | tv series | 2 | 1 | 0 | 1 | 0 | 1 | Netflix |
| 3 | 1212 | Ch:os:en | 2013 | 7 | 9 | NA | NA | Shahar Isaac,Jonathan Roumie,Noah James,Paras ... | Drama,History | United States | ... | A madly intense whirlwind drama about love, be... | 54 | tv series | 2 | 1 | 0 | 0 | 0 | 1 | Netflix |
| 4 | 505 | Breaking Bad | 2008 | 16 | 9 | 96 | NA | Bryan Cranston,Anna Gunn,Aaron Paul,Betsy Bran... | Crime,Drama,Thriller | United States | ... | When chemistry teacher Walter White is diagnos... | 49 | tv series | 5 | 1 | 0 | 0 | 0 | 1 | Netflix |
5 rows × 21 columns
fig = px.bar(y = netflix_imdb_high_tvshows['Title'][:15],
x = netflix_imdb_high_tvshows['IMDb'][:15],
color = netflix_imdb_high_tvshows['IMDb'][:15],
color_continuous_scale = 'Teal_r',
labels = { 'y' : 'TV Shows', 'x' : 'IMDb : Rating'},
title = 'TV Shows with Highest IMDb : Netflix')
fig.update_layout(plot_bgcolor = 'white')
fig.show()
fig = px.bar(y = netflix_imdb_low_tvshows['Title'][:15],
x = netflix_imdb_low_tvshows['IMDb'][:15],
color = netflix_imdb_low_tvshows['IMDb'][:15],
color_continuous_scale = 'Teal_r',
labels = { 'y' : 'TV Shows', 'x' : 'IMDb : Rating'},
title = 'TV Shows with Lowest IMDb : Netflix')
fig.update_layout(plot_bgcolor = 'white')
fig.show()
hulu_imdb_high_tvshows = df_imdb_high_tvshows.loc[df_imdb_high_tvshows['Hulu']==1].reset_index()
hulu_imdb_high_tvshows = hulu_imdb_high_tvshows.drop(['index'], axis = 1)
hulu_imdb_low_tvshows = df_imdb_low_tvshows.loc[df_imdb_low_tvshows['Hulu']==1].reset_index()
hulu_imdb_low_tvshows = hulu_imdb_low_tvshows.drop(['index'], axis = 1)
hulu_imdb_high_tvshows.head(5)
| ID | Title | Year | Age | IMDb | Rotten Tomatoes | Directors | Cast | Genres | Country | ... | Plotline | Runtime | Kind | Seasons | Netflix | Hulu | Prime Video | Disney+ | Type | Service Provider | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 3395 | Hungry Henry | 2014 | NR | 9 | NA | NA | NA | NA | United States | ... | NA | 11 | tv series | 2 | 0 | 1 | 0 | 0 | 1 | Hulu |
| 1 | 2694 | Land of Honor | 2014 | 16 | 9 | NA | NA | Jun Gong,Zhehan Zhang,Ye Zhou,Gong Jun,Ma Wen ... | Action,Drama,Fantasy,History | China | ... | The Haves and the Have Nots is a primetime cab... | NA | tv series | 1 | 0 | 1 | 0 | 0 | 1 | Hulu |
| 2 | 589 | Death Note | 2006 | 18 | 9 | 100 | NA | Mamoru Miyano,Brad Swaile,Vincent Tong,Ryô Nai... | Animation,Crime,Drama,Fantasy,Mystery,Thriller | Japan | ... | On Nadia's 36th birthday she is struck by a ca... | 24 | tv series | 1 | 1 | 1 | 0 | 0 | 1 | Netflix |
| 3 | 2664 | The Joy of Painting | 1983 | 0 | 9 | NA | NA | Bob Ross,Steve Ross,Dana Jester,Peep,John Tham... | Documentary,Family | United States | ... | The Winslow family is a pretty normal family e... | 30 | tv series | 31 | 0 | 1 | 1 | 0 | 1 | Prime Video |
| 4 | 3606 | The Adventures of Dr. Buckeye Bottoms | 2017 | NR | 9 | NA | NA | Bartholomew Buckeye Bottoms,Zac Fine | Reality-TV | United States | ... | NA | NA | tv series | 2 | 0 | 1 | 0 | 0 | 1 | Hulu |
5 rows × 21 columns
fig = px.bar(y = hulu_imdb_high_tvshows['Title'][:15],
x = hulu_imdb_high_tvshows['IMDb'][:15],
color = hulu_imdb_high_tvshows['IMDb'][:15],
color_continuous_scale = 'Teal_r',
labels = { 'y' : 'TV Shows', 'x' : 'IMDb : Rating'},
title = 'TV Shows with Highest IMDb : Hulu')
fig.update_layout(plot_bgcolor = 'white')
fig.show()
fig = px.bar(y = hulu_imdb_low_tvshows['Title'][:15],
x = hulu_imdb_low_tvshows['IMDb'][:15],
color = hulu_imdb_low_tvshows['IMDb'][:15],
color_continuous_scale = 'Teal_r',
labels = { 'y' : 'TV Shows', 'x' : 'IMDb : Rating'},
title = 'TV Shows with Lowest IMDb : Hulu')
fig.update_layout(plot_bgcolor = 'white')
fig.show()
prime_video_imdb_high_tvshows = df_imdb_high_tvshows.loc[df_imdb_high_tvshows['Prime Video']==1].reset_index()
prime_video_imdb_high_tvshows = prime_video_imdb_high_tvshows.drop(['index'], axis = 1)
prime_video_imdb_low_tvshows = df_imdb_low_tvshows.loc[df_imdb_low_tvshows['Prime Video']==1].reset_index()
prime_video_imdb_low_tvshows = prime_video_imdb_low_tvshows.drop(['index'], axis = 1)
prime_video_imdb_high_tvshows.head(5)
| ID | Title | Year | Age | IMDb | Rotten Tomatoes | Directors | Cast | Genres | Country | ... | Plotline | Runtime | Kind | Seasons | Netflix | Hulu | Prime Video | Disney+ | Type | Service Provider | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 5129 | Tanks! | 2005 | 7 | 10 | NA | NA | David Fletcher,Graham McTavish,John Erickson,B... | History,War | United States | ... | In this series Tom Hubbard travels throughout ... | NA | tv series | 1 | 0 | 0 | 1 | 0 | 1 | Prime Video |
| 1 | 3718 | The Sopranos | 1999 | 18 | 9 | 92 | NA | James Gandolfini,Edie Falco,Michael Imperioli,... | Crime,Drama | United States | ... | Harry Bosch is an irreverent homicide detectiv... | 55 | tv series | 6 | 0 | 0 | 1 | 0 | 1 | Prime Video |
| 2 | 144 | The Chosen | 1981 | 7 | 9 | 75 | NA | Shahar Isaac,Jonathan Roumie,Noah James,Paras ... | Drama,History | United States | ... | Depressed after the passing of his father (Dha... | 54 | tv series | 2 | 0 | 0 | 1 | 0 | 1 | Prime Video |
| 3 | 4124 | Harmony with A R Rahman | 2018 | NR | 9 | NA | NA | A.R. Rahman,Ustad Mohi Baha'uddin Dagar,Sajith... | Documentary,Musical | India | ... | Our thirties and forties are the busiest time ... | NA | tv series | 1 | 0 | 0 | 1 | 0 | 1 | Prime Video |
| 4 | 1576 | Raja Rasoi Aur Anya Kahaniyan | 2015 | NR | 9 | NA | NA | Manwendra Tripathy | History | India | ... | Amamiya Shuuhei moves from Tokyo to the countr... | 45 | tv series | 2 | 1 | 0 | 1 | 0 | 1 | Netflix |
5 rows × 21 columns
fig = px.bar(y = prime_video_imdb_high_tvshows['Title'][:15],
x = prime_video_imdb_high_tvshows['IMDb'][:15],
color = prime_video_imdb_high_tvshows['IMDb'][:15],
color_continuous_scale = 'Teal_r',
labels = { 'y' : 'TV Shows', 'x' : 'IMDb : Rating'},
title = 'TV Shows with Highest IMDb : Prime Video')
fig.update_layout(plot_bgcolor = 'white')
fig.show()
fig = px.bar(y = prime_video_imdb_low_tvshows['Title'][:15],
x = prime_video_imdb_low_tvshows['IMDb'][:15],
color = prime_video_imdb_low_tvshows['IMDb'][:15],
color_continuous_scale = 'Teal_r',
labels = { 'y' : 'TV Shows', 'x' : 'IMDb : Rating'},
title = 'TV Shows with Lowest IMDb : Prime Video')
fig.update_layout(plot_bgcolor = 'white')
fig.show()
disney_imdb_high_tvshows = df_imdb_high_tvshows.loc[df_imdb_high_tvshows['Disney+']==1].reset_index()
disney_imdb_high_tvshows = disney_imdb_high_tvshows.drop(['index'], axis = 1)
disney_imdb_low_tvshows = df_imdb_low_tvshows.loc[df_imdb_low_tvshows['Disney+']==1].reset_index()
disney_imdb_low_tvshows = disney_imdb_low_tvshows.drop(['index'], axis = 1)
disney_imdb_high_tvshows.head(5)
| ID | Title | Year | Age | IMDb | Rotten Tomatoes | Directors | Cast | Genres | Country | ... | Plotline | Runtime | Kind | Seasons | Netflix | Hulu | Prime Video | Disney+ | Type | Service Provider | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 5304 | The Imagineering Story | 2019 | 0 | 9 | 100 | NA | Tom Morris,Kevin Rafferty,Angela Bassett,Tom F... | Documentary | United States | ... | Raven Baxter is a teenager. She can see glimps... | 60 | tv series | 1 | 0 | 0 | 0 | 1 | 1 | Disney+ |
| 1 | 493 | The Other Me | 2000 | 0 | 9 | NA | Sotiris Tsafoulias | Pigmalion Dadakaridis,Petros Lagoutis,Vicky Pa... | Crime,Drama,Mystery,Thriller | Greece | ... | NA | 45 | tv series | 2 | 0 | 0 | 0 | 1 | 1 | Disney+ |
| 2 | 483 | Avatar | 2009 | 13 | 9 | 82 | NA | Dee Bradley Baker,Zach Tyler,Mae Whitman,Jack ... | Animation,Action,Adventure,Family,Fantasy,Mystery | United States | ... | In a suburban fantasy world, two teenage elf b... | 23 | tv series | 3 | 0 | 0 | 0 | 1 | 1 | Disney+ |
| 3 | 1037 | Brain Games | 2011 | 0 | 8 | NA | NA | Jason Silva,Bert Thomas Morris,Apollo Robbins,... | Documentary,Comedy,Drama,Game-Show,Reality-TV | United States | ... | NA | 60 | tv series | 6 | 1 | 0 | 0 | 1 | 1 | Netflix |
| 4 | 2490 | Star vs. the Forces of Evil | 2015 | 7 | 8 | NA | NA | Eden Sher,Adam McArthur,Grey Griffin,Daron Nef... | Animation,Action,Adventure,Comedy,Drama,Family... | United States,Spain,United Kingdom,Mexico,Japan | ... | Set in 2008 and against the hugely atmospheric... | 22 | tv series | 4 | 0 | 1 | 0 | 1 | 1 | Disney+ |
5 rows × 21 columns
fig = px.bar(y = disney_imdb_high_tvshows['Title'][:15],
x = disney_imdb_high_tvshows['IMDb'][:15],
color = disney_imdb_high_tvshows['IMDb'][:15],
color_continuous_scale = 'Teal_r',
labels = { 'y' : 'TV Shows', 'x' : 'IMDb : Rating'},
title = 'TV Shows with Highest IMDb : Disney+')
fig.update_layout(plot_bgcolor = 'white')
fig.show()
fig = px.bar(y = disney_imdb_low_tvshows['Title'][:15],
x = disney_imdb_low_tvshows['IMDb'][:15],
color = disney_imdb_low_tvshows['IMDb'][:15],
color_continuous_scale = 'Teal_r',
labels = { 'y' : 'TV Shows', 'x' : 'IMDb : Rating'},
title = 'TV Shows with Lowest IMDb : Disney+')
fig.update_layout(plot_bgcolor = 'white')
fig.show()
print(f'''
The TV Show with Highest IMDb Ever Got is '{df_imdb_high_tvshows['Title'][0]}' : '{df_imdb_high_tvshows['IMDb'].max()}'\n
The TV Show with Lowest IMDb Ever Got is '{df_imdb_low_tvshows['Title'][0]}' : '{df_imdb_low_tvshows['IMDb'].min()}'\n
The TV Show with Highest IMDb on 'Netflix' is '{netflix_imdb_high_tvshows['Title'][0]}' : '{netflix_imdb_high_tvshows['IMDb'].max()}'\n
The TV Show with Lowest IMDb on 'Netflix' is '{netflix_imdb_low_tvshows['Title'][0]}' : '{netflix_imdb_low_tvshows['IMDb'].min()}'\n
The TV Show with Highest IMDb on 'Hulu' is '{hulu_imdb_high_tvshows['Title'][0]}' : '{hulu_imdb_high_tvshows['IMDb'].max()}'\n
The TV Show with Lowest IMDb on 'Hulu' is '{hulu_imdb_low_tvshows['Title'][0]}' : '{hulu_imdb_low_tvshows['IMDb'].min()}'\n
The TV Show with Highest IMDb on 'Prime Video' is '{prime_video_imdb_high_tvshows['Title'][0]}' : '{prime_video_imdb_high_tvshows['IMDb'].max()}'\n
The TV Show with Lowest IMDb on 'Prime Video' is '{prime_video_imdb_low_tvshows['Title'][0]}' : '{prime_video_imdb_low_tvshows['IMDb'].min()}'\n
The TV Show with Highest IMDb on 'Disney+' is '{disney_imdb_high_tvshows['Title'][0]}' : '{disney_imdb_high_tvshows['IMDb'].max()}'\n
The TV Show with Lowest IMDb on 'Disney+' is '{disney_imdb_low_tvshows['Title'][0]}' : '{disney_imdb_low_tvshows['IMDb'].min()}'\n
''')
The TV Show with Highest IMDb Ever Got is 'Tanks!' : '10'
The TV Show with Lowest IMDb Ever Got is 'PINKFONG!' : '1'
The TV Show with Highest IMDb on 'Netflix' is 'Africa' : '9'
The TV Show with Lowest IMDb on 'Netflix' is 'Game Winning Hit' : '2'
The TV Show with Highest IMDb on 'Hulu' is 'Hungry Henry' : '9'
The TV Show with Lowest IMDb on 'Hulu' is 'My Super Sweet 16' : '1'
The TV Show with Highest IMDb on 'Prime Video' is 'Tanks!' : '10'
The TV Show with Lowest IMDb on 'Prime Video' is 'PINKFONG!' : '1'
The TV Show with Highest IMDb on 'Disney+' is 'The Imagineering Story' : '9'
The TV Show with Lowest IMDb on 'Disney+' is 'Bizaardvark' : '3'
print(f'''
Accross All Platforms the Average IMDb is '{round(df_tvshows_imdb['IMDb'].mean(), ndigits = 2)}'\n
The Average IMDb on 'Netflix' is '{round(netflix_imdb_tvshows['IMDb'].mean(), ndigits = 2)}'\n
The Average IMDb on 'Hulu' is '{round(hulu_imdb_tvshows['IMDb'].mean(), ndigits = 2)}'\n
The Average IMDb on 'Prime Video' is '{round(prime_video_imdb_tvshows['IMDb'].mean(), ndigits = 2)}'\n
The Average IMDb on 'Disney+' is '{round(disney_imdb_tvshows['IMDb'].mean(), ndigits = 2)}'\n
''')
Accross All Platforms the Average IMDb is '6.7'
The Average IMDb on 'Netflix' is '6.77'
The Average IMDb on 'Hulu' is '6.64'
The Average IMDb on 'Prime Video' is '6.71'
The Average IMDb on 'Disney+' is '6.58'
f, ax = plt.subplots(1, 2 , figsize = (20, 5))
sns.distplot(df_tvshows_imdb['IMDb'],bins = 20, kde = True, ax = ax[0])
sns.boxplot(df_tvshows_imdb['IMDb'], ax = ax[1])
plt.show()
# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('IMDb s Per Platform')
# Plotting the information from each dataset into a histogram
sns.histplot(prime_video_imdb_tvshows['IMDb'][:100], color = 'lightblue', legend = True, kde = True)
sns.histplot(netflix_imdb_tvshows['IMDb'][:100], color = 'red', legend = True, kde = True)
sns.histplot(hulu_imdb_tvshows['IMDb'][:100], color = 'lightgreen', legend = True, kde = True)
sns.histplot(disney_imdb_tvshows['IMDb'][:100], color = 'darkblue', legend = True, kde = True)
# Setting the legend
plt.legend(['Prime Video', 'Netflix', 'Hulu', 'Disney+'])
plt.show()
def round_val(data):
if str(data) != 'nan':
return round(data)
df_tvshows_imdb_group['IMDb Group'] = df_tvshows_imdb['IMDb'].apply(round_val)
imdb_values = df_tvshows_imdb_group['IMDb Group'].value_counts().sort_index(ascending = False).tolist()
imdb_index = df_tvshows_imdb_group['IMDb Group'].value_counts().sort_index(ascending = False).index
# imdb_values, imdb_index
imdb_group_count = df_tvshows_imdb_group.groupby('IMDb Group')['Title'].count()
imdb_group_tvshows = df_tvshows_imdb_group.groupby('IMDb Group')[['Netflix', 'Hulu', 'Prime Video', 'Disney+']].sum()
imdb_group_data_tvshows = pd.concat([imdb_group_count, imdb_group_tvshows], axis = 1).reset_index().rename(columns = {'Title' : 'TV Shows Count'})
imdb_group_data_tvshows = imdb_group_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)
# IMDb Group with TV Shows Counts - All Platforms Combined
imdb_group_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)
| IMDb Group | TV Shows Count | Netflix | Hulu | Prime Video | Disney+ | |
|---|---|---|---|---|---|---|
| 6 | 7 | 1956 | 737 | 603 | 694 | 53 |
| 7 | 8 | 1147 | 456 | 339 | 432 | 41 |
| 5 | 6 | 1065 | 415 | 316 | 349 | 55 |
| 4 | 5 | 404 | 139 | 119 | 156 | 22 |
| 3 | 4 | 163 | 45 | 57 | 62 | 7 |
| 2 | 3 | 61 | 17 | 25 | 23 | 1 |
| 8 | 9 | 53 | 18 | 12 | 27 | 3 |
| 1 | 2 | 19 | 4 | 10 | 6 | 0 |
| 0 | 1 | 7 | 0 | 3 | 5 | 0 |
| 9 | 10 | 1 | 0 | 0 | 1 | 0 |
imdb_group_data_tvshows.sort_values(by = 'IMDb Group', ascending = False)
| IMDb Group | TV Shows Count | Netflix | Hulu | Prime Video | Disney+ | |
|---|---|---|---|---|---|---|
| 9 | 10 | 1 | 0 | 0 | 1 | 0 |
| 8 | 9 | 53 | 18 | 12 | 27 | 3 |
| 7 | 8 | 1147 | 456 | 339 | 432 | 41 |
| 6 | 7 | 1956 | 737 | 603 | 694 | 53 |
| 5 | 6 | 1065 | 415 | 316 | 349 | 55 |
| 4 | 5 | 404 | 139 | 119 | 156 | 22 |
| 3 | 4 | 163 | 45 | 57 | 62 | 7 |
| 2 | 3 | 61 | 17 | 25 | 23 | 1 |
| 1 | 2 | 19 | 4 | 10 | 6 | 0 |
| 0 | 1 | 7 | 0 | 3 | 5 | 0 |
fig = px.bar(y = imdb_group_data_tvshows['TV Shows Count'],
x = imdb_group_data_tvshows['IMDb Group'],
color = imdb_group_data_tvshows['IMDb Group'],
color_continuous_scale = 'Teal_r',
labels = { 'y' : 'TV Shows Count', 'x' : 'IMDb : Rating'},
title = 'TV Shows with Group IMDb : All Platforms')
fig.update_layout(plot_bgcolor = "white")
fig.show()
fig = px.pie(imdb_group_data_tvshows[:10],
names = imdb_group_data_tvshows['IMDb Group'],
values = imdb_group_data_tvshows['TV Shows Count'],
color = imdb_group_data_tvshows['TV Shows Count'],
color_discrete_sequence = px.colors.sequential.Teal)
fig.update_traces(textinfo = 'percent+label',
title = 'TV Shows Count based on IMDb Group')
fig.show()
df_imdb_group_high_tvshows = imdb_group_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False).reset_index()
df_imdb_group_high_tvshows = df_imdb_group_high_tvshows.drop(['index'], axis = 1)
# filter = (imdb_group_data_tvshows['TV Shows Count'] == (imdb_group_data_tvshows['TV Shows Count'].max()))
# df_imdb_group_high_tvshows = imdb_group_data_tvshows[filter]
# highest_rated_tvshows = imdb_group_data_tvshows.loc[imdb_group_data_tvshows['TV Shows Count'].idxmax()]
# print('\nIMDb with Highest Ever TV Shows Count are : All Platforms Combined\n')
df_imdb_group_high_tvshows.head(5)
| IMDb Group | TV Shows Count | Netflix | Hulu | Prime Video | Disney+ | |
|---|---|---|---|---|---|---|
| 0 | 7 | 1956 | 737 | 603 | 694 | 53 |
| 1 | 8 | 1147 | 456 | 339 | 432 | 41 |
| 2 | 6 | 1065 | 415 | 316 | 349 | 55 |
| 3 | 5 | 404 | 139 | 119 | 156 | 22 |
| 4 | 4 | 163 | 45 | 57 | 62 | 7 |
df_imdb_group_low_tvshows = imdb_group_data_tvshows.sort_values(by = 'TV Shows Count', ascending = True).reset_index()
df_imdb_group_low_tvshows = df_imdb_group_low_tvshows.drop(['index'], axis = 1)
# filter = (imdb_group_data_tvshows['TV Shows Count'] = = (imdb_group_data_tvshows['TV Shows Count'].min()))
# df_imdb_group_low_tvshows = imdb_group_data_tvshows[filter]
# print('\nIMDb with Lowest Ever TV Shows Count are : All Platforms Combined\n')
df_imdb_group_low_tvshows.head(5)
| IMDb Group | TV Shows Count | Netflix | Hulu | Prime Video | Disney+ | |
|---|---|---|---|---|---|---|
| 0 | 10 | 1 | 0 | 0 | 1 | 0 |
| 1 | 1 | 7 | 0 | 3 | 5 | 0 |
| 2 | 2 | 19 | 4 | 10 | 6 | 0 |
| 3 | 9 | 53 | 18 | 12 | 27 | 3 |
| 4 | 3 | 61 | 17 | 25 | 23 | 1 |
print(f'''
Total '{df_tvshows_imdb['IMDb'].count()}' Titles are available on All Platforms, out of which\n
You Can Choose to see TV Shows from Total '{imdb_group_data_tvshows['IMDb Group'].unique().shape[0]}' IMDb Group, They were Like this, \n
{imdb_group_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)['IMDb Group'].unique()} etc. \n
The IMDb Group with Highest TV Shows Count have '{imdb_group_data_tvshows['TV Shows Count'].max()}' TV Shows Available is '{df_imdb_group_high_tvshows['IMDb Group'][0]}', &\n
The IMDb Group with Lowest TV Shows Count have '{imdb_group_data_tvshows['TV Shows Count'].min()}' TV Shows Available is '{df_imdb_group_low_tvshows['IMDb Group'][0]}'
''')
Total '4876' Titles are available on All Platforms, out of which
You Can Choose to see TV Shows from Total '10' IMDb Group, They were Like this,
[ 7 8 6 5 4 3 9 2 1 10] etc.
The IMDb Group with Highest TV Shows Count have '1956' TV Shows Available is '7', &
The IMDb Group with Lowest TV Shows Count have '1' TV Shows Available is '10'
netflix_imdb_group_tvshows = imdb_group_data_tvshows[imdb_group_data_tvshows['Netflix'] != 0].sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_imdb_group_tvshows = netflix_imdb_group_tvshows.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)
netflix_imdb_group_high_tvshows = df_imdb_group_high_tvshows.sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_imdb_group_high_tvshows = netflix_imdb_group_high_tvshows.drop(['index'], axis = 1)
netflix_imdb_group_low_tvshows = df_imdb_group_high_tvshows.sort_values(by = 'Netflix', ascending = True).reset_index()
netflix_imdb_group_low_tvshows = netflix_imdb_group_low_tvshows.drop(['index'], axis = 1)
netflix_imdb_group_high_tvshows.head(5)
| IMDb Group | TV Shows Count | Netflix | Hulu | Prime Video | Disney+ | |
|---|---|---|---|---|---|---|
| 0 | 7 | 1956 | 737 | 603 | 694 | 53 |
| 1 | 8 | 1147 | 456 | 339 | 432 | 41 |
| 2 | 6 | 1065 | 415 | 316 | 349 | 55 |
| 3 | 5 | 404 | 139 | 119 | 156 | 22 |
| 4 | 4 | 163 | 45 | 57 | 62 | 7 |
hulu_imdb_group_tvshows = imdb_group_data_tvshows[imdb_group_data_tvshows['Hulu'] != 0].sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_imdb_group_tvshows = hulu_imdb_group_tvshows.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)
hulu_imdb_group_high_tvshows = df_imdb_group_high_tvshows.sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_imdb_group_high_tvshows = hulu_imdb_group_high_tvshows.drop(['index'], axis = 1)
hulu_imdb_group_low_tvshows = df_imdb_group_high_tvshows.sort_values(by = 'Hulu', ascending = True).reset_index()
hulu_imdb_group_low_tvshows = hulu_imdb_group_low_tvshows.drop(['index'], axis = 1)
hulu_imdb_group_high_tvshows.head(5)
| IMDb Group | TV Shows Count | Netflix | Hulu | Prime Video | Disney+ | |
|---|---|---|---|---|---|---|
| 0 | 7 | 1956 | 737 | 603 | 694 | 53 |
| 1 | 8 | 1147 | 456 | 339 | 432 | 41 |
| 2 | 6 | 1065 | 415 | 316 | 349 | 55 |
| 3 | 5 | 404 | 139 | 119 | 156 | 22 |
| 4 | 4 | 163 | 45 | 57 | 62 | 7 |
prime_video_imdb_group_tvshows = imdb_group_data_tvshows[imdb_group_data_tvshows['Prime Video'] != 0].sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_imdb_group_tvshows = prime_video_imdb_group_tvshows.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'TV Shows Count'], axis = 1)
prime_video_imdb_group_high_tvshows = df_imdb_group_high_tvshows.sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_imdb_group_high_tvshows = prime_video_imdb_group_high_tvshows.drop(['index'], axis = 1)
prime_video_imdb_group_low_tvshows = df_imdb_group_high_tvshows.sort_values(by = 'Prime Video', ascending = True).reset_index()
prime_video_imdb_group_low_tvshows = prime_video_imdb_group_low_tvshows.drop(['index'], axis = 1)
prime_video_imdb_group_high_tvshows.head(5)
| IMDb Group | TV Shows Count | Netflix | Hulu | Prime Video | Disney+ | |
|---|---|---|---|---|---|---|
| 0 | 7 | 1956 | 737 | 603 | 694 | 53 |
| 1 | 8 | 1147 | 456 | 339 | 432 | 41 |
| 2 | 6 | 1065 | 415 | 316 | 349 | 55 |
| 3 | 5 | 404 | 139 | 119 | 156 | 22 |
| 4 | 4 | 163 | 45 | 57 | 62 | 7 |
disney_imdb_group_tvshows = imdb_group_data_tvshows[imdb_group_data_tvshows['Disney+'] != 0].sort_values(by = 'Disney+', ascending = False).reset_index()
disney_imdb_group_tvshows = disney_imdb_group_tvshows.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'TV Shows Count'], axis = 1)
disney_imdb_group_high_tvshows = df_imdb_group_high_tvshows.sort_values(by = 'Disney+', ascending = False).reset_index()
disney_imdb_group_high_tvshows = disney_imdb_group_high_tvshows.drop(['index'], axis = 1)
disney_imdb_group_low_tvshows = df_imdb_group_high_tvshows.sort_values(by = 'Disney+', ascending = True).reset_index()
disney_imdb_group_low_tvshows = disney_imdb_group_low_tvshows.drop(['index'], axis = 1)
disney_imdb_group_high_tvshows.head(5)
| IMDb Group | TV Shows Count | Netflix | Hulu | Prime Video | Disney+ | |
|---|---|---|---|---|---|---|
| 0 | 6 | 1065 | 415 | 316 | 349 | 55 |
| 1 | 7 | 1956 | 737 | 603 | 694 | 53 |
| 2 | 8 | 1147 | 456 | 339 | 432 | 41 |
| 3 | 5 | 404 | 139 | 119 | 156 | 22 |
| 4 | 4 | 163 | 45 | 57 | 62 | 7 |
print(f'''
The IMDb Group with Highest TV Shows Count Ever Got is '{df_imdb_group_high_tvshows['IMDb Group'][0]}' : '{df_imdb_group_high_tvshows['TV Shows Count'].max()}'\n
The IMDb Group with Lowest TV Shows Count Ever Got is '{df_imdb_group_low_tvshows['IMDb Group'][0]}' : '{df_imdb_group_low_tvshows['TV Shows Count'].min()}'\n
The IMDb Group with Highest TV Shows Count on 'Netflix' is '{netflix_imdb_group_high_tvshows['IMDb Group'][0]}' : '{netflix_imdb_group_high_tvshows['Netflix'].max()}'\n
The IMDb Group with Lowest TV Shows Count on 'Netflix' is '{netflix_imdb_group_low_tvshows['IMDb Group'][0]}' : '{netflix_imdb_group_low_tvshows['Netflix'].min()}'\n
The IMDb Group with Highest TV Shows Count on 'Hulu' is '{hulu_imdb_group_high_tvshows['IMDb Group'][0]}' : '{hulu_imdb_group_high_tvshows['Hulu'].max()}'\n
The IMDb Group with Lowest TV Shows Count on 'Hulu' is '{hulu_imdb_group_low_tvshows['IMDb Group'][0]}' : '{hulu_imdb_group_low_tvshows['Hulu'].min()}'\n
The IMDb Group with Highest TV Shows Count on 'Prime Video' is '{prime_video_imdb_group_high_tvshows['IMDb Group'][0]}' : '{prime_video_imdb_group_high_tvshows['Prime Video'].max()}'\n
The IMDb Group with Lowest TV Shows Count on 'Prime Video' is '{prime_video_imdb_group_low_tvshows['IMDb Group'][0]}' : '{prime_video_imdb_group_low_tvshows['Prime Video'].min()}'\n
The IMDb Group with Highest TV Shows Count on 'Disney+' is '{disney_imdb_group_high_tvshows['IMDb Group'][0]}' : '{disney_imdb_group_high_tvshows['Disney+'].max()}'\n
The IMDb Group with Lowest TV Shows Count on 'Disney+' is '{disney_imdb_group_low_tvshows['IMDb Group'][0]}' : '{disney_imdb_group_low_tvshows['Disney+'].min()}'\n
''')
The IMDb Group with Highest TV Shows Count Ever Got is '7' : '1956'
The IMDb Group with Lowest TV Shows Count Ever Got is '10' : '1'
The IMDb Group with Highest TV Shows Count on 'Netflix' is '7' : '737'
The IMDb Group with Lowest TV Shows Count on 'Netflix' is '1' : '0'
The IMDb Group with Highest TV Shows Count on 'Hulu' is '7' : '603'
The IMDb Group with Lowest TV Shows Count on 'Hulu' is '10' : '0'
The IMDb Group with Highest TV Shows Count on 'Prime Video' is '7' : '694'
The IMDb Group with Lowest TV Shows Count on 'Prime Video' is '10' : '1'
The IMDb Group with Highest TV Shows Count on 'Disney+' is '6' : '55'
The IMDb Group with Lowest TV Shows Count on 'Disney+' is '2' : '0'
fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
n_i_ax1 = sns.barplot(x = netflix_imdb_group_tvshows['IMDb Group'][:10], y = netflix_imdb_group_tvshows['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_i_ax2 = sns.barplot(x = hulu_imdb_group_tvshows['IMDb Group'][:10], y = hulu_imdb_group_tvshows['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_i_ax3 = sns.barplot(x = prime_video_imdb_group_tvshows['IMDb Group'][:10], y = prime_video_imdb_group_tvshows['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_i_ax4 = sns.barplot(x = disney_imdb_group_tvshows['IMDb Group'][:10], y = disney_imdb_group_tvshows['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
n_i_ax1.title.set_text(labels[0])
h_i_ax2.title.set_text(labels[1])
p_i_ax3.title.set_text(labels[2])
d_i_ax4.title.set_text(labels[3])
plt.show()
plt.figure(figsize = (20, 5))
sns.lineplot(x = imdb_group_data_tvshows['IMDb Group'], y = imdb_group_data_tvshows['Netflix'], color = 'red')
sns.lineplot(x = imdb_group_data_tvshows['IMDb Group'], y = imdb_group_data_tvshows['Hulu'], color = 'lightgreen')
sns.lineplot(x = imdb_group_data_tvshows['IMDb Group'], y = imdb_group_data_tvshows['Prime Video'], color = 'lightblue')
sns.lineplot(x = imdb_group_data_tvshows['IMDb Group'], y = imdb_group_data_tvshows['Disney+'], color = 'darkblue')
plt.xlabel('IMDb Group', fontsize = 15)
plt.ylabel('TV Shows Count', fontsize = 15)
plt.show()
print(f'''
Accross All Platforms Total Count of IMDb Group is '{imdb_group_data_tvshows['IMDb Group'].unique().shape[0]}'\n
Total Count of IMDb Group on 'Netflix' is '{netflix_imdb_group_tvshows['IMDb Group'].unique().shape[0]}'\n
Total Count of IMDb Group on 'Hulu' is '{hulu_imdb_group_tvshows['IMDb Group'].unique().shape[0]}'\n
Total Count of IMDb Group on 'Prime Video' is '{prime_video_imdb_group_tvshows['IMDb Group'].unique().shape[0]}'\n
Total Count of IMDb Group on 'Disney+' is '{disney_imdb_group_tvshows['IMDb Group'].unique().shape[0]}'\n
''')
Accross All Platforms Total Count of IMDb Group is '10'
Total Count of IMDb Group on 'Netflix' is '8'
Total Count of IMDb Group on 'Hulu' is '9'
Total Count of IMDb Group on 'Prime Video' is '10'
Total Count of IMDb Group on 'Disney+' is '7'
fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
n_i_ax1 = sns.lineplot(y = imdb_group_data_tvshows['IMDb Group'], x = imdb_group_data_tvshows['Netflix'], color = 'red', ax = axes[0, 0])
h_i_ax2 = sns.lineplot(y = imdb_group_data_tvshows['IMDb Group'], x = imdb_group_data_tvshows['Hulu'], color = 'lightgreen', ax = axes[0, 1])
p_i_ax3 = sns.lineplot(y = imdb_group_data_tvshows['IMDb Group'], x = imdb_group_data_tvshows['Prime Video'], color = 'lightblue', ax = axes[1, 0])
d_i_ax4 = sns.lineplot(y = imdb_group_data_tvshows['IMDb Group'], x = imdb_group_data_tvshows['Disney+'], color = 'darkblue', ax = axes[1, 1])
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
n_i_ax1.title.set_text(labels[0])
h_i_ax2.title.set_text(labels[1])
p_i_ax3.title.set_text(labels[2])
d_i_ax4.title.set_text(labels[3])
plt.show()
fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
n_i_ax1 = sns.barplot(x = imdb_group_data_tvshows['IMDb Group'][:10], y = imdb_group_data_tvshows['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_i_ax2 = sns.barplot(x = imdb_group_data_tvshows['IMDb Group'][:10], y = imdb_group_data_tvshows['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_i_ax3 = sns.barplot(x = imdb_group_data_tvshows['IMDb Group'][:10], y = imdb_group_data_tvshows['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_i_ax4 = sns.barplot(x = imdb_group_data_tvshows['IMDb Group'][:10], y = imdb_group_data_tvshows['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
n_i_ax1.title.set_text(labels[0])
h_i_ax2.title.set_text(labels[1])
p_i_ax3.title.set_text(labels[2])
d_i_ax4.title.set_text(labels[3])
plt.show()